stepfun · Open weights
Step 3.7 Flash Thinking
Step 3.7 Flash Thinking is StepFun's high-efficiency multimodal MoE model with visible reasoning enabled for deeper agentic coding, long-context reasoning, tool use, and native image/video understanding. ⚠️ Note: This model routes through StepFun, so privacy and logging guarantees may be limited.
- Reasoning
- Tools
- Vision
- Structured output
- Video input
- Input
- Text, Images, Video
- Output
- Text
- Reasoning effort
- none · low · medium · high
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.20
- Output
- $1.15
- Cache read
- $0.04
Reference prices as published by the model provider. API example
Specifications
- Context window
- 262.1K
- Max output
- 256K
- Average output (7 days)
- 7.1K tokens
- Longer than 99% of 468 models
Side by side
Step 3.7 Flash Thinking compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Step 3.7 Flash ThinkingstepfunThis model | Ministral 14BMistralRemove | |
|---|---|---|
| Provider | stepfun | Mistral |
| Discovery tier | Open weights | Open weights |
| Added | May 29, 2026 | Dec 4, 2025 |
| Limits | ||
| Context window | 262.14K | 262.14K |
| Max output | 256KBest | 32.77K |
| Average output | 7.1K tokens | 176 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.20 | $0.20 |
| Output | $1.15 | $0.20Best |
| Cache read | $0.04 | — |
| Performance | ||
| Request success (24h) | 100.0% | — |
| Benchmark indexes | ||
| Intelligence Index | — | 6.0 |
| Coding Index | — | 14.4 |
| Math Index | — | 30.0 |
| Capabilities | ||
| Reasoning | Yes | No |
| Tools | Yes | No |
| Vision | Yes | No |
| Structured output | Yes | No |
| Video input | Yes | No |
| Reasoning effort | none, low, medium, high | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Step 3.7 Flash Thinking
- Ministral 14B
Intelligence Index
- Step 3.7 Flash Thinking—
- Ministral 14B6.0
Indexes
Coding Index
Composite of the coding evaluations
- Step 3.7 Flash Thinking: —
- Ministral 14B: 14.4
Math Index
Composite of the math evaluations
- Step 3.7 Flash Thinking: —
- Ministral 14B: 30.0
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- Step 3.7 Flash Thinking: —
- Ministral 14B: 0.6%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- Step 3.7 Flash Thinking: —
- Ministral 14B: 0.2%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- Step 3.7 Flash Thinking: —
- Ministral 14B: 131 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- Step 3.7 Flash Thinking: —
- Ministral 14B: 247 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- Step 3.7 Flash Thinking: —
- Ministral 14B: 1.2%
AA-LCRv1.1
Reasoning across long documents
- Step 3.7 Flash Thinking: —
- Ministral 14B: 26.3%
MLCR-AA
Long-context reasoning over medical records
- Step 3.7 Flash Thinking: —
- Ministral 14B: 2.2%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Step 3.7 Flash Thinking: —
- Ministral 14B: 4.6%
GPQA Diamond
Graduate-level science questions
- Step 3.7 Flash Thinking: —
- Ministral 14B: 57.2%
MMLU-Pro
Multi-subject knowledge and reasoning
- Step 3.7 Flash Thinking: —
- Ministral 14B: 69.3%
IFBench
Following precise output instructions
- Step 3.7 Flash Thinking: —
- Ministral 14B: 32.0%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- Step 3.7 Flash Thinking: —
- Ministral 14B: 0.0%
SciCode
Scientific computing in Python
- Step 3.7 Flash Thinking: —
- Ministral 14B: 23.8%
LiveCodeBench
Recent competitive programming problems
- Step 3.7 Flash Thinking: —
- Ministral 14B: 35.1%
Math
AIME 2025
Competition mathematics, 2025 problems
- Step 3.7 Flash Thinking: —
- Ministral 14B: 30.0%
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- Step 3.7 Flash Thinking: —
- Ministral 14B: 4.5%
τ²-Bench Telecom
Tool use in a customer-support simulation
- Step 3.7 Flash Thinking: —
- Ministral 14B: 27.2%
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Step 3.7 Flash Thinking: —
- Ministral 14B: 26.3%
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Prompt cache hits
- 0.0%
- About $0.20 per 1M input tokens with caching
- Request success (24h)
- 100.0%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "stepfun/step-3.7-flash:thinking",
"reasoning_effort": "medium",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="stepfun/step-3.7-flash:thinking",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)stepfun
Related models
Other stepfun models, starting with the same family.